Special Session 1

基础设施的快速数字化与地质数据的指数级增长，重塑着岩土工程与地质工程的发展格局。随着基础设施项目日趋复杂，且不断涉足更具挑战性的地质环境，传统经验分析法已难以应对地质条件的高维度、非线性及固有不确定性。人工智能（AI）、机器学习（ML）与大数据分析技术的融合应用，提供了变革性的解决方案，推动工程模式从经验驱动向数据驱动转型。

本专场旨在汇聚科研人员、工程师与数据科学家，共同探讨人工智能在地质工程领域的前沿应用。核心目标是搭建先进计算算法与岩土工程实际需求之间的桥梁，探索人工智能技术如何实现场地特征自动化表征、改进本构模型构建、优化设计与施工流程，以及提升地质结构体抵御自然灾害的韧性。专场将重点关注可解释人工智能与物理信息嵌入策略，以确保相关技术在地质工程应用中的可靠性与物理一致性。

现面向全球征集相关领域的摘要投稿，主题包括但不限于以下方向：

（1）智能场地表征与数据分析

（2）先进建模与预测分析

（3）智能施工与风险管理 

The rapid digitalization of civil infrastructure and the exponential growth of geological data are reshaping the landscape of geotechnical and geological engineering. As infrastructure projects become increasingly complex and enter more challenging geological environments, traditional empirical and analytical methods often struggle to handle the high dimensionality, non-linearity, and inherent uncertainty of geological conditions. The integration of Artificial Intelligence (AI), Machine Learning (ML), and Big Data analytics offers a transformative solution, shifting the paradigm from experience-based to data-centric engineering.

This special session aims to gather researchers, engineers, and data scientists to discuss the state-of-the-art applications of AI in geo-engineering. The goal is to bridge the gap between advanced computational algorithms and practical geotechnical challenges. We seek to explore how artificial intelligence can automate site characterization, enhance constitutive modeling, optimize design and construction processes, and improve the resilience of geo-structures against natural hazards. Special attention will be given to interpretable AI and physics-informed strategies that ensure reliability and physical consistency in geo-engineering applications.

We invite abstract submissions on topics including, but not limited to:

(1) Intelligent Site Characterization & Data Analysis

• Computer vision and deep learning for rock mass classification and soil stratigraphy identification.
  

• Subsurface data interpolation and 3D geological modeling using geo-statistics and machine learning.
  

• Handling sparse, noisy, and heterogeneous geotechnical data: Data augmentation and generation strategies.
  

• Automated processing of geo-data and laboratory test results.

(2) Advanced Modeling & Predictive Analytics

• Physics-Informed Machine Learning (i.e., PINNs) for solving complex boundary value problems in geomechanics.

• Data-driven constitutive modeling and parameter identification for soils and rocksTBM s.

• Surrogate modeling for real-time prediction of slope stability, tunnel convergence, and foundation settlement.

• Generative AI and Large Language Models (LLMs) for geotechnical report analysis and decision support.

(3) Smart Construction & Risk Management

• AI-driven optimization for TBM tunneling, drilling, and excavation parameters.

• Real-time monitoring and inverse analysis: Updating design parameters based on field performance data.
  

• Intelligent risk assessment and early warning systems for landslides, debris flows, and urban geohazards.

• Digital Twin integration: Linking AI algorithms with BIM and sensor networks for lifecycle management.

优秀摘要将被推荐向以下期刊的特刊提交完整论文：

Underground Space

ENGINEERING Structure and Civil Engineering （原名：Frontiers of Structural and Civil Engineering）

Civil Engineering Design